Types Of Biological Data Research Articles

The Potential Use of Targeted Proteomics and Metabolomics for the Identification and Monitoring of Diabetic Kidney Disease.

Diabetic kidney disease (DKD) is a prevalent microvascular complication of diabetes mellitus and is associated with a significantly worse prognosis compared to diabetic patients without kidney involvement, other microvascular complications, or non-diabetic chronic kidney disease, due to its higher risk of cardiovascular events, faster progression to end-stage kidney disease, and increased mortality. In clinical practice, diagnosis is based on estimated glomerular filtration rate (eGFR) and albuminuria. However, given the limitations of these diagnostic markers, novel biomarkers must be identified. Omics is a new field of study involving the comprehensive analysis of various types of biological data at the molecular level. In different fields, they have shown promising results in (early) detection of diseases, personalized medicine, therapeutic monitoring, and understanding pathogenesis. DKD is primarily utilized in scientific research and has not yet been implemented in routine clinical practice. The aim of this review is to provide an overview of currently available data on targeted omics. After an extensive literature search, 25 different (panels of) omics were withheld and analyzed. Both serum/plasma and urine proteomics and metabolomics have been described with varying degrees of evidence. For all omics, there is still a relative paucity of data from large, prospective, longitudinal cohorts, presumably because of the heterogeneity of DKD and the lack of patient selection in studies, the complexity of omics technologies, and various practical and ethical considerations (e.g., limited accessibility, cost, and privacy concerns).

Geothermal ecosystems on Mt. Erebus, Antarctica, support diverse and taxonomically novel biota.

Mt. Erebus, Antarctica, is the southernmost active volcano in the world and harbors diverse geothermally unique ecosystems, including 'Subglacial' and 'Exposed' features, surrounded by a vast desert of ice and snow. Previous studies, while limited in scope, have highlighted the unique and potentially endemic biota of Mt. Erebus. Here, we provide an amplicon-based biodiversity study across all domains of life and all types of geothermal features, with physicochemical and biological data from 48 samples (39 Exposed and 9 Subglacial) collected through various field seasons. We found potentially high taxonomic novelty among prokaryotes and fungi, supporting past hypotheses of high endemism due to the distinctive and isolated environment; in particular, the large number of taxonomically divergent fungal sequences was surprising. We found that different site types had unique physicochemistry and biota; Exposed sites were warmer than Subglacial (median: 40 vs 10°C for Exposed and Subglacial, respectively) and tended to have more photosynthetic organisms (Cyanobacteria and Chlorophyta). Subglacial sites had more Actinobacteriota, correlated with greater concentrations of Ca and Mg present. Our results also suggest potential human impacts on these remote, highly significant sites, finding evidence for fungal taxa normally associated with wood decay. In this study, we provide a blueprint for future work aimed at better understanding the novel biota of Mt. Erebus.

Multi-omics association study of DNA methylation and gene expression levels and diagnoses of cardiovascular diseases in Danish Twins

BackgroundCardiovascular diseases (CVDs) are major causes of mortality and morbidity worldwide; yet the understanding of their molecular basis is incomplete. Multi-omics studies have significant potential to uncover these mechanisms, but such studies are challenged by genetic and environmental confounding—a problem that can be effectively reduced by investigating intrapair differences in twins. Here, we linked data on all diagnoses of the circulatory system from the nationwide Danish Patient Registry (spanning 1977–2022) to a study population of 835 twins holding genome-wide DNA methylation and gene expression data. CVD diagnoses were divided into prevalent or incident cases (i.e., occurring before or after blood sample collection (2007–2011)). The diagnoses were classified into four groups: cerebrovascular diseases, coronary artery disease (CAD), arterial and other cardiovascular diseases (AOCDs), and diseases of the veins and lymphatic system. Statistical analyses were performed by linear (prevalent cases) or cox (incident cases) regression analyses at both the individual-level and twin pair-level. Significant genes (p < 0.05) in both types of biological data and at both levels were inspected by bioinformatic analyses, including gene set enrichment analysis and interaction network analysis.ResultsIn general, more genes were found for prevalent than for incident cases, and bioinformatic analyses primarily found pathways of the immune system, signal transduction and diseases for prevalent cases, and pathways of cell–cell communication, metabolisms of proteins and RNA, gene expression, and chromatin organization groups for incident cases. This potentially reflects biology related to response to CVD (prevalent cases) and mechanisms related to regulation and development of disease (incident cases). Of specific genes, Myosin 1E was found to be central for CAD, and DEAD-Box Helicase 5 for AOCD. These genes were observed in both the prevalent and the incident analyses, potentially reflecting that their DNA methylation and gene transcription levels change both because of disease (prevalent cases) and prior disease (incident cases).ConclusionWe present novel biomarkers for CVD by performing multi-omics analysis in twins, hereby lowering the confounding due to shared genetics and early life environment—a study design that is surprisingly rare in the field of CVD, and where additional studies are highly needed.

An overview of multi-omics technologies in rheumatoid arthritis: applications in biomarker and pathway discovery.

Rheumatoid arthritis (RA) is a chronic inflammatory autoimmune disease with a complex pathological mechanism involving autoimmune response, local inflammation and bone destruction. Metabolic pathways play an important role in immune-related diseases and their immune responses. The pathogenesis of rheumatoid arthritis may be related to its metabolic dysregulation. Moreover, histological techniques, including genomics, transcriptomics, proteomics and metabolomics, provide powerful tools for comprehensive analysis of molecular changes in biological systems. The present study explores the molecular and metabolic mechanisms of RA, emphasizing the central role of metabolic dysregulation in the RA disease process and highlighting the complexity of metabolic pathways, particularly metabolic remodeling in synovial tissues and its association with cytokine-mediated inflammation. This paper reveals the potential of histological techniques in identifying metabolically relevant therapeutic targets in RA; specifically, we summarize the genetic basis of RA and the dysregulated metabolic pathways, and explore their functional significance in the context of immune cell activation and differentiation. This study demonstrates the critical role of histological techniques in decoding the complex metabolic network of RA and discusses the integration of histological data with other types of biological data.

Using adjusted local assortativity with Molecular Pixelation unveils colocalization of membrane proteins with immunological significance.

Advances in spatial proteomics and protein colocalization are a driving force in the understanding of cellular mechanisms and their influence on biological processes. New methods in the field of spatial proteomics call for the development of algorithms and open up new avenues of research. The newly introduced Molecular Pixelation (MPX) provides spatial information on surface proteins and their relationship with each other in single cells. This allows for in silico representation of neighborhoods of membrane proteins as graphs. In order to analyze this new data modality, we adapted local assortativity in networks of MPX single-cell graphs and created a method that is able to capture detailed information on the spatial relationships of proteins. The introduced method can evaluate the pairwise colocalization of proteins and access higher-order similarity to investigate the colocalization of multiple proteins at the same time. We evaluated the method using publicly available MPX datasets where T cells were treated with a chemokine to study uropod formation. We demonstrate that adjusted local assortativity detects the effects of the stimuli at both single- and multiple-marker levels, which enhances our understanding of the uropod formation. We also applied our method to treating cancerous B-cell lines using a therapeutic antibody. With the adjusted local assortativity, we recapitulated the effect of rituximab on the polarity of CD20. Our computational method together with MPX improves our understanding of not only the formation of cell polarity and protein colocalization under stimuli but also advancing the overall insight into immune reaction and reorganization of cell surface proteins, which in turn allows the design of novel therapies. We foresee its applicability to other types of biological spatial data when represented as undirected graphs.

An interpretable deep learning model predicts RNA–small molecule binding sites

The intricate interplay between RNA molecules and small ligands plays a pivotal role in regulating biological processes, underscoring the necessity for accurate prediction models of RNA–small molecule binding sites. In this study, we develop CapBind, a novel interpretive deep learning framework utilizing a Capsule Network architecture, to precisely identify RNA–small molecule binding sites. This framework stands out for its multifaceted approach, which leverages both the sequence and structural information of RNA as input features, allowing for a thorough understanding of the complex interactions between RNA and small molecules. Leveraging multi-source bioinformatics data, including the distribution of RNA secondary structures, our model characterizes sequence and structural features with unparalleled depth. Through a unified alignment of these multi-source feature representations, we achieve dimensional homogeneity in the potential feature maps for both types of biological data. The crux of our methodology lies in the deployment of a multi-level Capsule Network, engineered to identify the nuanced interactions of RNA sequences with small molecules. The essence of our approach resides in the implementation of a multi-layered Capsule Network. Utilizing a sophisticated routing mechanism, this network demonstrates unparalleled efficacy in learning and identifying the intricate interactions between RNA sequences and small molecules. This mechanism enables dynamic adjustment of information flow across multiple levels, thereby capturing subtle features and patterns that might elude conventional neural network architectures. The experimental results demonstrate the superior performance of our model, particularly highlighting its progress in evaluation metrics compared to current state-of-the-art models. Case studies further validate the model’s precision in identifying binding sites, offering potential insights into gene expression pathways and novel therapeutic avenues for neurodegenerative diseases. Moreover, an extensive interpretability analysis of our silicon model reveals the internal interaction mechanisms between specific RNA regions and small molecules, contributing valuable perspectives for drug design and molecular biology research. These findings underscore the model’s predictive accuracy and biological applicability, establishing our approach as a significant leap forward in the computational prediction of RNA–small molecule binding sites.

Multi-omics data integration and drug screening of AML cancer using Generative Adversarial Network

In the era of precision medicine, accurate disease phenotype prediction for heterogeneous diseases, such as cancer, is emerging due to advanced technologies that link genotypes and phenotypes. However, it is difficult to integrate different types of biological data because they are so varied. In this study, we focused on predicting the traits of a blood cancer called Acute Myeloid Leukemia (AML) by combining different kinds of biological data. We used a recently developed method called Omics Generative Adversarial Network (GAN) to better classify cancer outcomes. The primary advantages of a GAN include its ability to create synthetic data that is nearly indistinguishable from real data, its high flexibility, and its wide range of applications, including multi-omics data analysis. In addition, the GAN was effective at combining two types of biological data. We created synthetic datasets for gene activity and DNA methylation. Our method was more accurate in predicting disease traits than using the original data alone. The experimental results provided evidence that the creation of synthetic data through interacting multi-omics data analysis using GANs improves the overall prediction quality. Furthermore, we identified the top-ranked significant genes through statistical methods and pinpointed potential candidate drug agents through in-silico studies. The proposed drugs, also supported by other independent studies, might play a crucial role in the treatment of AML cancer. The code is available on GitHub; https://github.com/SabrinAfroz/omicsGAN_codes?fbclid=IwAR1-/stuffmlE0hyWgSu2wlXo6dYlKUei3faLdlvpxTOOUPVlmYCloXf4Uk9ejK4I

DRSPRING: Graph convolutional network (GCN)-Based drug synergy prediction utilizing drug-induced gene expression profile

Great efforts have been made over the years to identify novel drug pairs with synergistic effects. Although numerous computational approaches have been proposed to analyze diverse types of biological big data, the pharmacogenomic profiles, presumably the most direct proxy of drug effects, have been rarely used due to the data sparsity problem. In this study, we developed a composite deep-learning-based model that predicts the drug synergy effect utilizing pharmacogenomic profiles as well as molecular properties. Graph convolutional network (GCN) was used to represent and integrate the chemical structure, genetic interactions, drug-target information, and gene expression profiles of cell lines. Insufficient amount of pharmacogenomic data, i.e., drug-induced expression profiles from the LINCS project, was resolved by augmenting the data with the predicted profiles. Our method learned and predicted the Loewe synergy score in the DrugComb database and achieved a better or comparable performance compared to other published methods in a benchmark test. We also investigated contribution of various input features, which highlighted the value of basal gene expression and pharmacogenomic profiles of each cell line. Importantly, DRSPRING (DRug Synergy PRediction by INtegrated GCN) can be applied to any drug pairs and any cell lines, greatly expanding its applicability compared to previous methods.

GENETIC ARCHIVES AND LIFELINE: UNRAVELING THE UMBILICAL CORD’S BIOLOGICAL DATABASE

Biological databases are critical components of the field of bioinformatics, which is dedicated to managing, organising, and making sense of the vast and diverse biological data generated by scientific research. These databases play a fundamental role in modern life sciences, allowing researchers, clinicians, and scientists to access, analyse, and interpret a wide range of biological information. These databases serve as invaluable resources, enabling researchers to access, manage, and analyse biological data, accelerating scientific discoveries and enhancing our understanding of life's complexities. There are various types of biological databases that serve as critical resources for researchers and scientists in the field of life sciences. These databases are categorised based on the types of biological data they store and manage. Keywords: Bioinformatics, biological database, genetics, scientific research, genomics, medical advancements, data repositories

Data-driven mathematical and visualization approaches for removing rare features for Compositional Data Analysis (CoDA).

Sparse feature tables, in which many features are present in very few samples, are common in big biological data (e.g.metagenomics). Ignoring issues of zero-laden datasets can result in biased statistical estimates and decreased power in downstream analyses. Zeros are also a particular issue for compositional data analysis using log-ratios since the log of zero is undefined. Researchers typically deal with this issue by removing low frequency features, but the thresholds for removal differ markedly between studies with little or no justification. Here, we present CurvCut, an unsupervised data-driven approach with human confirmation for rare-feature removal. CurvCut implements two distinct approaches for determining natural breaks in the feature distributions: a method based on curvature analysis borrowed from thermodynamics and the Fisher-Jenks statistical method. Our results show that CurvCut rapidly identifies data-specific breaks in these distributions that can be used as cutoff points for low-frequency feature removal that maximizes feature retention. We show that CurvCut works across different biological data types and rapidly generates clear visual results that allow researchers to confirm and apply feature removal cutoffs to individual datasets.

Representation Learning of Biological Concepts: A Systematic Review

Objective: Representation learning in the context of biological concepts involves acquiring their numerical representations through various sources of biological information, such as sequences, interactions, and literature. This study has conducted a comprehensive systematic review by analyzing both quantitative and qualitative data to provide an overview of this field. Methods: Our systematic review involved searching for articles on the representation learning of biological concepts in PubMed and EMBASE databases. Among the 507 articles published between 2015 and 2022, we carefully screened and selected 65 papers for inclusion. We then developed a structured workflow that involved identifying relevant biological concepts and data types, reviewing various representation learning techniques, and evaluating downstream applications for assessing the quality of the learned representations. Results: The primary focus of this review was on the development of numerical representations for gene/DNA/RNA entities. We have found Word2Vec to be the most commonly used method for biological representation learning. Moreover, several studies are increasingly utilizing state-of-the-art large language models to learn numerical representations of biological concepts. We also observed that representations learned from specific sources were typically used for single downstream applications that were relevant to the source. Conclusion: Existing methods for biological representation learning are primarily focused on learning representations from a single data type, with the output being fed into predictive models for downstream applications. Although there have been some studies that have explored the use of multiple data types to improve the performance of learned representations, such research is still relatively scarce. In this systematic review, we have provided a summary of the data types, models, and downstream applications used in this task.

A deep learning-based framework for predicting survival-associated groups in colon cancer by integrating multi-omics and clinical data

Precise prognostic classification of patients and identifying survival subgroups and their associated genes can be important clinical references when designing treatment strategies for cancer patients. Multi-omics and data integration techniques are powerful tools to achieve this goal. This study aimed to introduce a machine learning method to integrate three types of biological data, and investigate the performance of two other methods, in identifying the survival dependency of patients. The data included TCGA RNA-seq gene expression, DNA methylation, and clinical data from 368 patients with colon cancer also we use an independent external validation data set, containing 232 samples. Three methods including, hyper-parameter optimized autoencoders (HPOAE), normal autoencoder, and penalized principal component analysis (PPCA) were used for simultaneous data integration and estimation under a COX hazards model. The HPOAE was thought to outperform other methods. The HPOAE had the Log Rank Mantel-Cox value of 14.27 ± 2, and a Breslow-Generalized Wilcoxon value of 13.13 ± 1. Ten miRNA, 11 methylated genes, and 28 mRNA all by (importance of marginal cutoff > 0.95) were identified. The study demonstrated that hsa-miR-485-5p targets both ZMYM1 and tp53, the latter of which has been previously associated with cancer in numerous studies. Furthermore, compared to other methods, the HPOAE exhibited a greater capacity for identifying survival subgroups and the genes associated with them in patients with colon cancer. However, all of the results were obtained by computational methods, and clinical and experimental studies are needed to validate these results.

Graph deep neural network for discovery of multi‐omic subnetworks related to Alzheimer’s Disease

AbstractBackgroundThe recent multi‐omics analysis explores the integration of multiple biological data types, which can suggest a more comprehensive view of biological processes underlying complex diseases, such as Alzheimer’s disease (AD). Various biological networks have been leveraged as prior knowledge with attempt to discovery of more interpretable multi‐omics markers [1]. We applied a new graph neural network to take advantage of this rich prior knowledge together with multi‐omics data for identification of system‐level AD markers.MethodWe used GWAS genotype, RNA‐Seq gene expression, and protein expression data from the ROS/MAP Project. In total, 133 subjects with full set of ‐omics features were included in the study (Table. 1). There are 1,751 functionally connected ‐omics features in the prior biological network, including 186 peptides, 743 unique genes, and 822 single‐nucleotide polymorphisms (SNPs). Multi‐omic network of functional connections between SNPs, genes and proteins were created based on the REACTOME database, SNP‐gene mapping relationship and the SNP2TFBS database [2]. This network was applied to guide the architecture design of the neural network. The input layer consists of all ‐omics features. A biological drop‐connect layer of Varmole was set as for transparent layer that duplicate of protein and gene nodes in the input layer [3]. Links between input layer and transparent layer were added based on the prior multi‐omic network. In addition, we also added self‐connection links for all genes and proteins.ResultOur proposed integrated multi‐omic DNN largely outperforms other state‐of‐the‐art models (Table. 2). With cut‐off at 0.00001, 538 features were identified as discriminative. Three largest connected components were observed with more than 30 nodes (Fig. 1), among which 28 SNPs, 309 genes and 31 proteins form the largest connected component. Top hub nodes are proteins PIK3R1, GRB2, FYN. Shown in Fig. 2 is the list of top REACTOME pathways enriched by genes and proteins in the largest connected component [4].ConclusionIntegrated multi‐omic DNN identified multi‐mic subnetworks with great predictive power, providing critical functional connections contributing to AD. [1] Xie, et al., BIB, 2021. [2] Fabregat et al., NAR, 2018. [3] Nguyen, et al., Bioinformatics, 2021. [4] Kanehisa, et al., NAR, 2000.

MantaID: a machine learning-based tool to automate the identification of biological database IDs.

The number of biological databases is growing rapidly, but different databases use different identifiers (IDs) to refer to the same biological entity. The inconsistency in IDs impedes the integration of various types of biological data. To resolve the problem, we developed MantaID, a data-driven, machine learning-based approach that automates identifying IDs on a large scale. The MantaID model's prediction accuracy was proven to be 99%, and it correctly and effectively predicted 100,000 ID entries within 2 min. MantaID supports the discovery and exploitation of ID from large quantities of databases (e.g. up to 542 biological databases). An easy-to-use freely available open-source software R package, a user-friendly web application and application programming interfaces were also developed for MantaID to improve applicability. To our knowledge, MantaID is the first tool that enables an automatic, quick, accurate and comprehensive identification of large quantities of IDs and can therefore be used as a starting point to facilitate the complex assimilation and aggregation of biological data across diverse databases.

Improved Computational Drug-Repositioning by Self-Paced Non-Negative Matrix Tri-Factorization.

Drug repositioning (DR) is a strategy to find new targets for existing drugs, which plays an important role in reducing the costs, time, and risk of traditional drug development. Recently, the matrix factorization approach has been widely used in the field of DR prediction. Nevertheless, there are still two challenges: 1) Learning ability deficiencies, the model cannot accurately predict more potential associations. 2) Easy to fall into a bad local optimal solution, the model tends to get a suboptimal result. In this study, we propose a self-paced non-negative matrix tri-factorization (SPLNMTF) model, which integrates three types of different biological data from patients, genes, and drugs into a heterogeneous network through non-negative matrix tri-factorization, thereby learning more information to improve the learning ability of the model. In the meantime, the SPLNMTF model sequentially includes samples into training from easy (high-quality) to complex (low-quality) in the soft weighting way, which effectively alleviates falling into a bad local optimal solution to improve the prediction performance of the model. The experimental results on two real datasets of ovarian cancer and acute myeloid leukemia (AML) show that SPLNMTF outperforms the other eight state-of-the-art models and gets better prediction performance in drug repositioning. The data and source code are available at: https://github.com/qi0906/SPLNMTF.

Importance of timely metadata curation to the global surveillance of genetic diversity.

Genetic diversity within species represents a fundamental yet underappreciated level of biodiversity. Because genetic diversity can indicate species resilience to changing climate, its measurement is relevant to many national and global conservation policy targets. Many studies produce large amounts of genome-scale genetic diversity data for wild populations, but most (87%) do not include the associated spatial and temporal metadata necessary for them to be reused in monitoring programs or for acknowledging the sovereignty of nations or Indigenous peoples. We undertook a distributed datathon to quantify the availability of these missing metadata and to test the hypothesis that their availability decays with time. We also worked to remediate missing metadata by extracting them from associated published papers, online repositories, and direct communication with authors. Starting with 848 candidate genomic data sets (reduced representation and whole genome) from the International Nucleotide Sequence Database Collaboration, we determined that 561 contained mostly samples from wild populations. We successfully restored spatiotemporal metadata for 78% of these 561 data sets (n=440 data sets with data on 45,105 individuals from 762 species in 17 phyla). Examining papers and online repositories was much more fruitful than contacting 351 authors, who replied to our email requests 45% of the time. Overall, 23% of our email queries to authors unearthed useful metadata. The probability of retrieving spatiotemporal metadata declined significantly as age of the data set increased. There was a 13.5% yearly decrease in metadata associated with published papers or online repositories and up to a 22% yearly decrease in metadata that were only available from authors. This rapid decay in metadata availability, mirrored in studies of other types of biological data, should motivate swift updates to data-sharing policies and researcher practices to ensure that the valuable context provided by metadata is not lost to conservation science forever.

Omics Data and Data Representations for Deep Learning-Based Predictive Modeling.

Medical discoveries mainly depend on the capability to process and analyze biological datasets, which inundate the scientific community and are still expanding as the cost of next-generation sequencing technologies is decreasing. Deep learning (DL) is a viable method to exploit this massive data stream since it has advanced quickly with there being successive innovations. However, an obstacle to scientific progress emerges: the difficulty of applying DL to biology, and this because both fields are evolving at a breakneck pace, thus making it hard for an individual to occupy the front lines of both of them. This paper aims to bridge the gap and help computer scientists bring their valuable expertise into the life sciences. This work provides an overview of the most common types of biological data and data representations that are used to train DL models, with additional information on the models themselves and the various tasks that are being tackled. This is the essential information a DL expert with no background in biology needs in order to participate in DL-based research projects in biomedicine, biotechnology, and drug discovery. Alternatively, this study could be also useful to researchers in biology to understand and utilize the power of DL to gain better insights into and extract important information from the omics data.

Identifying essential proteins from protein–protein interaction networks based on influence maximization

BackgroundEssential proteins are indispensable to the development and survival of cells. The identification of essential proteins not only is helpful for the understanding of the minimal requirements for cell survival, but also has practical significance in disease diagnosis, drug design and medical treatment. With the rapidly amassing of protein–protein interaction (PPI) data, computationally identifying essential proteins from protein–protein interaction networks (PINs) becomes more and more popular. Up to now, a number of various approaches for essential protein identification based on PINs have been developed.ResultsIn this paper, we propose a new and effective approach called iMEPP to identify essential proteins from PINs by fusing multiple types of biological data and applying the influence maximization mechanism to the PINs. Concretely, we first integrate PPI data, gene expression data and Gene Ontology to construct weighted PINs, to alleviate the impact of high false-positives in the raw PPI data. Then, we define the influence scores of nodes in PINs with both orthological data and PIN topological information. Finally, we develop an influence discount algorithm to identify essential proteins based on the influence maximization mechanism.ConclusionsWe applied our method to identifying essential proteins from saccharomyces cerevisiae PIN. Experiments show that our iMEPP method outperforms the existing methods, which validates its effectiveness and advantage.

MorbidGCN: prediction of multimorbidity with a graph convolutional network based on integration of population phenotypes and disease network.

Exploring multimorbidity relationships among diseases is of great importance for understanding their shared mechanisms, precise diagnosis and treatment. However, the landscape of multimorbidities is still far from complete due to the complex nature of multimorbidity. Although various types of biological data, such as biomolecules and clinical symptoms, have been used to identify multimorbidities, the population phenotype information (e.g. physical activity and diet) remains less explored for multimorbidity. Here, we present a graph convolutional network (GCN) model, named MorbidGCN, for multimorbidity prediction by integrating population phenotypes and disease network. Specifically, MorbidGCN treats the multimorbidity prediction as a missing link prediction problem in the disease network, where a novel feature selection method is embedded to select important phenotypes. Benchmarking results on two large-scale multimorbidity data sets, i.e. the UK Biobank (UKB) and Human Disease Network (HuDiNe) data sets, demonstrate that MorbidGCN outperforms other competitive methods. With MorbidGCN, 9742 and 14010 novel multimorbidities are identified in the UKB and HuDiNe data sets, respectively. Moreover, we notice that the selected phenotypes that are generally differentially distributed between multimorbidity patients and single-disease patients can help interpret multimorbidities and show potential for prognosis of multimorbidities.

Knowledge Transfer from Macro-world to Micro-world: Enhancing 3D Cryo-ET Classification through Fine-Tuning Video-based Deep Models.

Deep learning models have achieved remarkable success in a wide range of natural-world tasks, such as vision, language, and speech recognition. These accomplishments are largely attributed to the availability of open-source large-scale datasets. More importantly, pre-trained foundational modellearnings exhibit a surprising degree of transferability to downstream tasks, enabling efficient learning even with limited training examples. However, the application of such natural-domain models to the domain of tiny Cryo-Electron Tomography (Cryo-ET) images has been a relatively unexplored frontier. This research is motivated by the intuition that 3D Cryo-ET voxel data can be conceptually viewed as a sequence of progressively evolving video frames. Leveraging the above insight, we propose a novel approach that involves the utilization of 3D models pre-trained on large-scale video datasets to enhance Cryo-ET subtomogram classification. Our experiments, conducted on both simulated and real Cryo-ET datasets, reveal compelling results. The use of video initialization not only demonstrates improvements in classification accuracy but also substantially reduces training costs. Further analyses provide additional evidence of the value of video initialization in enhancing subtomogram feature extraction. Additionally, we observe that video initialization yields similar positive effects when applied to medical 3D classification tasks, underscoring the potential of cross-domain knowledge transfer from video-based models to advance the state-of-the-art in a wide range of biological and medical data types. https://github.com/xulabs/aitom.